On implementing addition in VLSI technology

In this paper we discuss the rules for evaluation of arithmetic algorithms based on the speed of their VLSI implementations. We present the rules which are simple enough to be useful for quick estimates, but yet reflect basic dependencies. By applying these rules we derived a simple scheme for VLSI implementation of addition (ALU), with a near minimal number of gates and small and regular area. Despite its simplicity, this scheme outperforms carry-lookahead and recurrence solver schemes as demonstrated by simulation of the actual implementation of examples. This is because the properties of the scheme are based on the dependencies and assumptions reflecting the real conditions existing in VLSI-CMOS technology. We discuss these results and demonstrate by actual implementation of examples that the measures based on the number of logic levels are not applicable to the new VLSI technologies. © 1988.